Training complete
Browse files
README.md
CHANGED
|
@@ -1,13 +1,13 @@
|
|
| 1 |
---
|
| 2 |
-
base_model: bert-base-cased
|
| 3 |
license: apache-2.0
|
|
|
|
|
|
|
|
|
|
| 4 |
metrics:
|
| 5 |
- precision
|
| 6 |
- recall
|
| 7 |
- f1
|
| 8 |
- accuracy
|
| 9 |
-
tags:
|
| 10 |
-
- generated_from_trainer
|
| 11 |
model-index:
|
| 12 |
- name: bert-finetuned-ner4
|
| 13 |
results: []
|
|
@@ -18,13 +18,13 @@ should probably proofread and complete it, then remove this comment. -->
|
|
| 18 |
|
| 19 |
# bert-finetuned-ner4
|
| 20 |
|
| 21 |
-
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
-
- Loss: 0.
|
| 24 |
-
- Precision: 0.
|
| 25 |
-
- Recall: 0.
|
| 26 |
-
- F1: 0.
|
| 27 |
-
- Accuracy: 0.
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
@@ -49,15 +49,22 @@ The following hyperparameters were used during training:
|
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
-
- num_epochs:
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
-
| Training Loss | Epoch | Step
|
| 57 |
-
|
| 58 |
-
| 0.
|
| 59 |
-
| 0.
|
| 60 |
-
| 0.
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 61 |
|
| 62 |
|
| 63 |
### Framework versions
|
|
@@ -65,4 +72,4 @@ The following hyperparameters were used during training:
|
|
| 65 |
- Transformers 4.42.4
|
| 66 |
- Pytorch 2.3.1+cu121
|
| 67 |
- Datasets 2.20.0
|
| 68 |
-
- Tokenizers 0.19.1
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
license: apache-2.0
|
| 3 |
+
base_model: bert-base-cased
|
| 4 |
+
tags:
|
| 5 |
+
- generated_from_trainer
|
| 6 |
metrics:
|
| 7 |
- precision
|
| 8 |
- recall
|
| 9 |
- f1
|
| 10 |
- accuracy
|
|
|
|
|
|
|
| 11 |
model-index:
|
| 12 |
- name: bert-finetuned-ner4
|
| 13 |
results: []
|
|
|
|
| 18 |
|
| 19 |
# bert-finetuned-ner4
|
| 20 |
|
| 21 |
+
This model is a fine-tuned version of [bert-base-cased](https://huggingface.co/bert-base-cased) on an unknown dataset.
|
| 22 |
It achieves the following results on the evaluation set:
|
| 23 |
+
- Loss: 0.1263
|
| 24 |
+
- Precision: 0.8887
|
| 25 |
+
- Recall: 0.9039
|
| 26 |
+
- F1: 0.8962
|
| 27 |
+
- Accuracy: 0.9859
|
| 28 |
|
| 29 |
## Model description
|
| 30 |
|
|
|
|
| 49 |
- seed: 42
|
| 50 |
- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
|
| 51 |
- lr_scheduler_type: linear
|
| 52 |
+
- num_epochs: 10
|
| 53 |
|
| 54 |
### Training results
|
| 55 |
|
| 56 |
+
| Training Loss | Epoch | Step | Validation Loss | Precision | Recall | F1 | Accuracy |
|
| 57 |
+
|:-------------:|:-----:|:-----:|:---------------:|:---------:|:------:|:------:|:--------:|
|
| 58 |
+
| 0.062 | 1.0 | 2489 | 0.0642 | 0.8268 | 0.8402 | 0.8334 | 0.9805 |
|
| 59 |
+
| 0.0369 | 2.0 | 4978 | 0.0669 | 0.8463 | 0.8771 | 0.8614 | 0.9828 |
|
| 60 |
+
| 0.0224 | 3.0 | 7467 | 0.0649 | 0.8452 | 0.8995 | 0.8715 | 0.9830 |
|
| 61 |
+
| 0.0121 | 4.0 | 9956 | 0.0765 | 0.8678 | 0.8982 | 0.8827 | 0.9843 |
|
| 62 |
+
| 0.0075 | 5.0 | 12445 | 0.0903 | 0.8805 | 0.8923 | 0.8863 | 0.9845 |
|
| 63 |
+
| 0.0041 | 6.0 | 14934 | 0.0917 | 0.8822 | 0.9015 | 0.8918 | 0.9851 |
|
| 64 |
+
| 0.0038 | 7.0 | 17423 | 0.1190 | 0.8876 | 0.8915 | 0.8895 | 0.9852 |
|
| 65 |
+
| 0.0015 | 8.0 | 19912 | 0.1148 | 0.8880 | 0.9075 | 0.8976 | 0.9857 |
|
| 66 |
+
| 0.0007 | 9.0 | 22401 | 0.1185 | 0.8858 | 0.9039 | 0.8948 | 0.9860 |
|
| 67 |
+
| 0.001 | 10.0 | 24890 | 0.1263 | 0.8887 | 0.9039 | 0.8962 | 0.9859 |
|
| 68 |
|
| 69 |
|
| 70 |
### Framework versions
|
|
|
|
| 72 |
- Transformers 4.42.4
|
| 73 |
- Pytorch 2.3.1+cu121
|
| 74 |
- Datasets 2.20.0
|
| 75 |
+
- Tokenizers 0.19.1
|
runs/Jul29_14-11-32_2aaea0a40520/events.out.tfevents.1722265739.2aaea0a40520.415.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0caa157055fbba3a417de5a813172cd33e499797b88ca62db88cdc1a48413d7e
|
| 3 |
+
size 569
|